[llvm] [LV, VP]VP intrinsics support for the Loop Vectorizer + adding new tail-folding mode using EVL. (PR #76172)

[Alexey Bataev via llvm-commits]

================
@@ -1201,20 +1240,75 @@ void VPlanTransforms::addActiveLaneMask(
   // Walk users of WideCanonicalIV and replace all compares of the form
   // (ICMP_ULE, WideCanonicalIV, backedge-taken-count) with an
   // active-lane-mask.
-  VPValue *BTC = Plan.getOrCreateBackedgeTakenCount();
-  for (VPUser *U : SmallVector<VPUser *>(WideCanonicalIV->users())) {
-    auto *CompareToReplace = dyn_cast<VPInstruction>(U);
-    if (!CompareToReplace ||
-        CompareToReplace->getOpcode() != Instruction::ICmp ||
-        CompareToReplace->getPredicate() != CmpInst::ICMP_ULE ||
-        CompareToReplace->getOperand(1) != BTC)
-      continue;
+  replaceHeaderPredicateWithIdiom(Plan, *LaneMask);
+}
 
-    assert(CompareToReplace->getOperand(0) == WideCanonicalIV &&
-           "WidenCanonicalIV must be the first operand of the compare");
-    CompareToReplace->replaceAllUsesWith(LaneMask);
-    CompareToReplace->eraseFromParent();
+/// Add a VPEVLBasedIVPHIRecipe and related recipes to \p Plan and
+/// replaces all uses except the canonical IV increment of
+/// VPCanonicalIVPHIRecipe with a VPEVLBasedIVPHIRecipe. VPCanonicalIVPHIRecipe
+/// is used only for loop iterations counting after this transformation.
+///
+/// The function uses the following definitions:
+///  %StartV is the canonical induction start value.
+///
+/// The function adds the following recipes:
+///
+/// vector.ph:
+/// ...
+///
+/// vector.body:
+/// ...
+/// %P = EXPLICIT-VECTOR-LENGTH-BASED-IV-PHI [ %StartV, %vector.ph ], [
+/// %NextEVL, %vector.body ] %EVL = EXPLICIT-VECTOR-LENGTH %P, original TC
+/// ...
+/// %NextEVL = EXPLICIT-VECTOR-LENGTH + %P, %EVL
+/// ...
+///
+void VPlanTransforms::addExplicitVectorLength(VPlan &Plan) {
+  VPBasicBlock *Header = Plan.getVectorLoopRegion()->getEntryBasicBlock();
+  auto *CanonicalIVPHI = Plan.getCanonicalIV();
+  VPValue *StartV = CanonicalIVPHI->getStartValue();
+
+  // Walk users of WideCanonicalIV and replace all compares of the form
+  // (ICMP_ULE, WideCanonicalIV, backedge-taken-count) with an
+  // all-true-mask.
+  Value *TrueMask =
+      ConstantInt::getTrue(CanonicalIVPHI->getScalarType()->getContext());
+  VPValue *VPTrueMask = Plan.getVPValueOrAddLiveIn(TrueMask);
+  replaceHeaderPredicateWithIdiom(Plan, *VPTrueMask, [](VPUser &U, unsigned) {
+    return isa<VPWidenMemoryInstructionRecipe>(U);
+  });
+  // Now create the ExplicitVectorLengthPhi recipe in the main loop.
+  auto *EVLPhi = new VPEVLBasedIVPHIRecipe(StartV, DebugLoc());
+  EVLPhi->insertAfter(CanonicalIVPHI);
+  auto *VPEVL = new VPInstruction(VPInstruction::ExplicitVectorLength,
+                                  {EVLPhi, Plan.getTripCount()});
+  VPEVL->insertBefore(*Header, Header->getFirstNonPhi());
+
+  auto *CanonicalIVIncrement =
+      cast<VPInstruction>(CanonicalIVPHI->getBackedgeValue());
+  VPSingleDefRecipe *OpVPEVL = VPEVL;
+  if (CanonicalIVPHI->getScalarType() !=
+      IntegerType::get(CanonicalIVPHI->getScalarType()->getContext(),
+                       /*NumBits=*/32)) {
+    OpVPEVL = new VPScalarCastRecipe(Instruction::ZExt, OpVPEVL,
+                                     CanonicalIVPHI->getScalarType());
+    OpVPEVL->insertBefore(CanonicalIVIncrement);
----------------
alexey-bataev wrote:

> Why depend on CanonicalIVIncrement, can simply place the cast and the bump after VPEVL in the header?

The increment is placed after CanonicalIVIncrement, so just want to keep ext close to next evl.

> 
> Canonical IV must have a type no smaller than i32?
> 
> Simply ask for the size of Canonical IV's scalar type, than compare if equal to i32?

Done.

https://github.com/llvm/llvm-project/pull/76172